From 44b7b38c93f87928553f269e773718428c9dcf3e Mon Sep 17 00:00:00 2001 From: DREMN2112 Date: Thu, 7 Nov 2024 16:53:55 +0800 Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- function.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/function.py b/function.py index 7aa8180..a0b4a97 100644 --- a/function.py +++ b/function.py @@ -58,6 +58,8 @@ def predict_logreg(inX, weights): import numpy as np +import numpy as np + def load_data(filepath): """ 从文件中加载数据，处理缺失数据，并将 '?' 替换为列的均值。 @@ -82,10 +84,9 @@ def load_data(filepath): # 将标签提取出来 label = int(line[-1]) - # 将特征转换为浮动数组 + # 将特征转换为浮动数组，'?' 替换为 np.nan features = line[:-1] # 去除标签部分 - # 用特征中的均值替换 '?'，并转换为 float - features = [float(f) if f != '?' else None for f in features] + features = [float(f) if f != '?' else np.nan for f in features] # 将数据和标签分别加入到列表 data.append(features) @@ -95,15 +96,16 @@ def load_data(filepath): data = np.array(data) labels = np.array(labels) - # 计算每列的均值，并用均值替换 None + # 计算每列的均值，并用均值替换 NaN col_means = np.nanmean(data, axis=0) # 计算每列的均值，忽略 NaN - # 将 None 替换为对应的列均值 + # 将 NaN 替换为对应的列均值 for i in range(data.shape[1]): data[:, i] = np.where(np.isnan(data[:, i]), col_means[i], data[:, i]) return data, labels + if __name__ == "__main__": # 加载训练集 X_train, y_train = load_data("./data/horse-colic.data")